ResearchTasksFree-form answer generationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedKLAR (OOD)GRPO38.13Accuracy12Jun 8, 2026KLAR (train)GRPO49.69Accuracy12Jun 8, 2026